Domain-Independent Deception: A New Taxonomy and Linguistic Analysis
This addresses the challenge of detecting diverse deceptive content (like fake news and phishing) for internet users and researchers, though it appears incremental as it synthesizes existing research rather than introducing a novel detection method.
The paper tackles the problem of deceptive attacks across multiple domains by proposing a new computational definition and taxonomy for domain-independent deception, then analyzes linguistic cues and demonstrates evidence for knowledge transfer between different deception forms.
Internet-based economies and societies are drowning in deceptive attacks. These attacks take many forms, such as fake news, phishing, and job scams, which we call ``domains of deception.'' Machine-learning and natural-language-processing researchers have been attempting to ameliorate this precarious situation by designing domain-specific detectors. Only a few recent works have considered domain-independent deception. We collect these disparate threads of research and investigate domain-independent deception. First, we provide a new computational definition of deception and break down deception into a new taxonomy. Then, we analyze the debate on linguistic cues for deception and supply guidelines for systematic reviews. Finally, we investigate common linguistic features and give evidence for knowledge transfer across different forms of deception.